December 2002
Volume 2, Issue 10
Free
OSA Fall Vision Meeting Abstract  |   December 2002
A computational model of color categorization based on statistics of natural images
Author Affiliations
  • Serguei Endrikhovski
    Eastman Kodak Company, Rochester, NY, USA
Journal of Vision December 2002, Vol.2, 16. doi:https://doi.org/10.1167/2.10.16
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Serguei Endrikhovski; A computational model of color categorization based on statistics of natural images. Journal of Vision 2002;2(10):16. https://doi.org/10.1167/2.10.16.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

A computational model of color categorization is presented. The main assumption of the model is that the structure of color categories originates from the statistical structure of the perceived color environment. The perceived color environment can be modeled as color statistics of natural images in some perceptual and approximately uniform color space (e.g., the CIELUV color space). The process of color categorization can be modeled as the grouping of the color statistics by clustering algorithms (e.g., K-means). The proposed computational model enables to predict the location, rank, and number of color categories. The model is examined on the basis of K-means clustering analysis of statistics of 630 natural images in the CIELUV color space. In general, the model predictions are consistent with data from psycholinguistic studies.

Endrikhovski, S.(2002). A computational model of color categorization based on statistics of natural images [Abstract]. Journal of Vision, 2( 10): 16, 16a, http://journalofvision.org/2/10/16/, doi:10.1167/2.10.16. [CrossRef]
×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×